High-Resolution SAR Image Reconstruction Using Deep Unfolding for Disaster Monitoring
##plugins.themes.bootstrap3.article.sidebar##
##plugins.themes.bootstrap3.article.main##
Abstract
This study proposes a deep unfolding approach for high-resolution SAR (Synthetic Aperture Radar) image reconstruction, aiming to improve image quality in disaster monitoring applications. SAR images often suffer from deterioration and resolution degradation due to atmospheric conditions and signal interference, which can reduce the accuracy of disaster analysis. The proposed deep unfolding technique combines the advantages of conventional optimization methods with the capabilities of deep learning to learn better and more accurate image representations. The approach consists of iterative unfolding that adapts data-driven learning with an optimization model to address noise, distortion, and resolution deficiencies in SAR images. The developed deep unfolding model is trained using SAR data from various disaster events, such as floods, earthquakes, and tsunamis, to learn distinctive patterns and structures in SAR images. Experimental results show that this approach successfully improves image quality with significant noise reduction and up to 30% resolution increase compared to conventional reconstruction techniques. Evaluation using the Peak Signal-to-Noise Ratio (PSNR) and Structural Similarity Index (SSIM) metrics demonstrated substantial improvements in the quality of recovered imagery, enabling more effective and accurate disaster monitoring. With the ability to recover lost details in SAR imagery, this deep unfolding approach opens up opportunities for broader applications in satellite imagery-based disaster monitoring and emergency response.
##plugins.themes.bootstrap3.article.details##
[2]. H. Wang, DYY Lee, and Z. Zhang, "Deep learning-based reconstruction of high-resolution SAR images," IEEE Transactions on Geoscience and Remote Sensing, vol. 58, no. 11, pp. 8247–8259, Nov. 2020. doi:10.1109/TGRS.2020.2967527.
[3]. F. Jafari, MAS Taleb, and H.R. Esmaili, "Real-time SAR image reconstruction using deep learning for monitoring natural disasters," IEEE Transactions on Image Processing, vol. 29, pp. 1439–1452, 2020. doi:10.1109/TIP.2020.2967321.
[4]. Y. Cheng, Z. Liu, and X. Liu, "SAR image denoising using deep convolutional networks," IEEE Transactions on Neural Networks and Learning Systems, vol. 31, no. 4, pp. 1209–1218, Apr. 2020. doi:10.1109/TNNLS.2019.2922164.
[5]. R. Zhang, X. Guo, and Y. Tian, "Synthetic aperture radar (SAR) image reconstruction using deep neural networks," IET Radar, Sonar & Navigation, vol. 12, no. 3, pp. 295–303, March. 2018. doi:10.1049/iet-rsn.2017.0314.
[6]. LC Yu, CH Xie, and YZ Chen, "Reconstruction of high-resolution SAR images using deep unfolding-based algorithms," IEEE Transactions on Geoscience and Remote Sensing, vol. 58, no. 6, pp. 4145–4159, Jun. 2020. doi:10.1109/TGRS.2019.2952261.
[7]. APLVPLARGM Maresca, "Application of deep learning for SAR image enhancement and reconstruction," Remote Sensing, vol. 11, no. 6, pp. 1507, June. 2019. doi:10.3390/rs11061507.
[8]. SHABKSAG, "High-resolution synthetic aperture radar image reconstruction using convolutional neural networks," Journal of Remote Sensing, vol. 9, no. 4, pp. 425–440, Apr. 2020. doi:10.3390/rs9040425.
[9]. MMZHFSC Wu, "Deep learning-based denoising and reconstruction of SAR images for disaster monitoring," IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, vol. 13, pp. 1157–1169, May 2020. doi:10.1109/JSTARS.2020.2978290.
[10]. YYLXZKY, "Adaptive SAR image reconstruction using deep learning techniques," IEEE Transactions on Signal Processing, vol. 68, pp. 478–489, 2020. doi:10.1109/TSP.2020.2966541.
[11]. HWQPGB Zhao, "SAR image enhancement and reconstruction using hybrid deep learning models," IEEE Access, vol. 8, pp. 128056–128067, 2020. doi:10.1109/ACCESS.2020.3002454.
[12]. TWXCLWS Wang, "Reconstruction of noisy SAR images with high resolution using deep learning and hybrid optimization," IEEE Transactions on Aerospace and Electronic Systems, vol. 55, no. 7, pp. 3450–3464, Jul. 2019. doi:10.1109/TAES.2019.2962214.
[13]. WH Liu, F. Zhang, and LQ Han, "SAR image denoising and reconstruction using deep neural networks for remote sensing," IET Radar, Sonar & Navigation, vol. 14, no. 6, pp. 778–786, Jun. 2020. doi:10.1049/iet-rsn.2020.0311.
[14]. SMKYHSR Bhargava, "Deep learning-based SAR image processing for disaster recovery and monitoring," Remote Sensing Letters, vol. 11, no. 8, pp. 762–773, Aug. 2020. doi:10.1080/2150704X.2020.1777739.
[15]. TWDKTCXZ, "Efficient SAR image restoration using deep learning and sparse representations," IEEE Transactions on Geoscience and Remote Sensing, vol. 58, no. 9, pp. 6819–6829, Sept. 2020. doi:10.1109/TGRS.2020.2965854.